Overall score
38.8
Rank #80 · B confidence
DeepSeek · stable
DeepSeek V3.1 Terminus is a open-weight model tracked via Artificial Analysis independent evaluations for capability comparison across coding, agents, and reasoning.
Overall score
38.8
Rank #80 · B confidence
Capability
38.2
14 eligible benchmark families
Coverage
67%
Confidence B
Benchmarks scored
14
14 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| AIME 2025 | mathematics | 89.6667% | 2026-07-15 |
| LiveCodeBenchRanking weighted | coding | 79.7884% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 79.1919% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 65% | 2026-07-15 |
| IFBench | instruction following | 57.0068% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 44.9438% | 2026-07-15 |
| SciCodeRanking weighted | coding | 40.625% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 37.1345% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 30.303% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 19.464% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 15.8763% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 15.2456% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 1.7143% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -24.3167 index | 2026-07-15 |
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: efficiency, value. The last source check for this exact model was 2026-07-15.
Related models
Exact variants remain separate even when they share a provider or family.
DeepSeek V4 · preview
DeepSeek V4 FlashDeepSeek V4 · preview
DeepSeek V3.2DeepSeek V3 · stable